Skills Explorer Add Skills

discernment-nudge

An agent skill by anthropics, from anthropics/skills. Tags: anthropic, documents, office.

What it does

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add anthropics/skills --skill discernment-nudge

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/anthropics/skills
cp -r skills/skills/discernment-nudge ~/.claude/skills/discernment-nudge

Safety box score

Grade A, minimal risk: 0 of 100 risk points, rated 2026-10-21. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill only changes how the assistant phrases certain answers: after substantive responses it may append a short “second look” question set once per conversation. It does not include executable code, network access, filesystem writes, secrets handling, or privilege changes; the main impact is on response style and user prompting.

Category levels, from 0 (none) to 3 (high)
CategoryLevelWhy
Code & shell execution0 (none)No scripts, shell commands, or code evaluation are included; the skill is plain markdown guidance only.
Network access0 (none)There is no downloading, uploading, or remote API call behavior described in the files.
Filesystem reach0 (none)The skill does not read, write, or delete files outside its own documentation.
Secrets & credentials0 (none)It does not request tokens, passwords, or access to secret stores, and it does not ask the user to paste secrets.
Privilege & persistence0 (none)No sudo, global installs, services, shell startup edits, or OS/gIT configuration changes are involved.
Instruction hijack surface0 (none)The instructions do not tell the agent to ignore its rules, hide behavior, or follow external instructions; they only define when to add follow-up questions.
Irreversible actions0 (none)It does not send messages, post, deploy, pay, book, or delete anything; it only influences the assistant’s reply format.
Transparency0 (none)All shipped content is readable markdown plus an Apache license; there are no binaries, installers, or decoded-at-runtime blobs.

Before installing

Rated 2026-10-21 by an automated review of 2 files from the skill's repository.

Source

Repository
anthropics/skills (all skills from this repository)
Path
skills/discernment-nudge/SKILL.md
Branch
main
Updated
2026-09-19